Maritime image dehazing based on Omni-Directional Perception and frequency-guided fusion

Abstract

Maritime image dehazing plays a crucial role in visual navigation and environmental perception. While existing methods based on physical models and deep learning have achieved certain progress in enhancing image contrast and detail restoration, they still face challenges in insufficient target detail extraction and over-smoothed backgrounds in complex maritime scenarios. To address these issues, this paper proposes an innovative network architecture featuring parallel feature perception and frequency-guided fusion, which improves dehazing performance through three aspects: feature extraction, feature fusion, and information optimization. Specifically, the Omni-Directional Perception Module enhances the perception of complex features by strengthening high-frequency target detail and low-frequency background feature extraction. The Frequency-Guided Feature Fusion Module achieves efficient local-global feature fusion through frequency decomposition and dynamic weighting mechanisms. The Discrete Entropy Constraint Loss further improves the naturalness and detail fidelity of dehazed results by optimizing image information distribution. Experimental results demonstrate that our method significantly enhances detail representation and background naturalness in complex scenarios, providing a promising solution for marine image dehazing.